Prompt Embedding Probes (PEP): Hallucination Detection in LLMs from Hidden States

arXiv:2608.08024 · cs.CL, cs.AI · Submitted 2026-08-08 · Read on arXiv

Zakhar Mrykhin, Valentin Malykh

cs.CL, cs.AI

Submitted: 2026-08-08

Updated: 2026-08-11

Comments: 10 pages, 7 figures. Code available at https://github.com/zazamrykh/internal_probing

Code: https://github.com/zazamrykh/internal_probing

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Hallucination — 51× in this paper · explained in 4 episodes
• Embeddings — 31× in this paper · explained in 2 episodes
• Linear Probe — 31× in this paper · explained in 3 episodes
• Hallucination Detection — 21× in this paper · explained in 2 episodes
• Linear Probes — 14× in this paper · explained in 2 episodes
• AUC — 11× in this paper · explained in 2 episodes
• Prompt Embedding Probes — 8× in this paper
• Generator — 6× in this paper · explained in 2 episodes
• Verification — 6× in this paper · explained in 2 episodes
• Cross-Model Transfer — 5× in this paper · explained in 2 episodes
• Benchmark — 3× in this paper · explained in 2 episodes
• Generalization — 3× in this paper · explained in 14 episodes
• Hyperparameters — 3× in this paper · explained in 2 episodes
• Language Models (LLMs) — 3× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 3× in this paper · explained in 9 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Cross-Dataset Transfer — 2× in this paper · explained in 2 episodes
• Linear Probing — 2× in this paper · explained in 3 episodes
• Papers — 2× in this paper · explained in 3 episodes
• Transformers — 2× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• LoRA Adapters — 1× in this paper · explained in 3 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 6 episodes
• Tokenization — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• Gemma 3 Technical Report
• Persona Vectors: Monitoring and Controlling Character Traits in Language Models
• Training Verifiers to Solve Math Word Problems
• Language Models (Mostly) Know What They Know
• Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs
• Real-Time Detection of Hallucinated Entities in Long-Form Generation
• Qwen3 Technical Report

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering